# US 2019/0172215 A1 · System and method for obstacle avoidance > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0172215 A1 - Document ID: US20190172215A1 - Status: Published application - Kind: A1 - Application number: 16/263,880 - Filed: 2019-01-31 - Published: 2019-06-06 - Earliest claimed: 2016-08-01 - Assignees: Sz Dji Technology Co., Ltd. - Applicants: Sz Dji Technology Co., Ltd. - Inventors: Honghui ZHANG; Lei HAN; Xiao HU - Web page: https://patentgrep.com/patent/US20190172215A1 ## CPC - G06T 7/593: from stereo images - B64U 10/13: Flying platforms - B64U 30/20: Rotors; Rotor supports - G05D 1/101: {specially adapted for aircraft} - G06T 7/579: from motion - G06T 7/74: {involving reference images or patches} - H04N 13/128: Adjusting depth or disparity - H04N 13/204: using stereoscopic image cameras (stereoscopic photography G03B35/00) - B64U 50/13: using external fans or propellers - B64U 2201/00: UAVs characterised by their flight controls - G06T 2207/10012: Stereo images - G06T 2207/10016: Video; Image sequence - G06T 2207/30244: Camera pose - H04N 2013/0081: {Depth or disparity estimation from stereoscopic image signals} - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A method for assisting obstacle avoidance of a mobile platform includes determining to use a detection mode from a plurality of detection modes, detecting a characteristic condition of the mobile platform with respect to an obstacle using the detection mode, and directing the mobile platform to avoid the obstacle based on the detected characteristic condition. ## Claims ### Claim 1 A method for assisting obstacle avoidance of a mobile platform, comprising: determining to use a detection mode from a plurality of detection modes; detecting a characteristic condition of the mobile platform with respect to an obstacle using the detection mode; and directing the mobile platform to avoid the obstacle based on the detected characteristic condition. ### Claim 2 (depends on 1) The method of claim 1, wherein detecting the characteristic condition comprises detecting an obstacle distance using the detection mode. ### Claim 3 (depends on 2) The method of claim 2, wherein: the detection mode comprises an operation mode of the mobile platform; and detecting the characteristic condition comprises performing motion estimation for the mobile platform with respect to the obstacle using the operation mode. ### Claim 4 (depends on 3) The method of claim 3, further comprising directing the mobile platform to avoid the obstacle based on at least one of the obstacle distance or the motion estimation. ### Claim 5 (depends on 4) The method of claim 4, wherein determining to use the detection mode comprises: obtaining a disparity between two images of the obstacle, the images being captured using an imaging device; comparing the disparity with a predetermined disparity threshold level; and selecting a monocular mode as the detection mode in response to the disparity being less than the predetermined disparity threshold level, and selecting a binocular mode as the detection mode in response to the disparity being greater than or equal to the predetermined disparity threshold level. ### Claim 6 (depends on 5) The method of claim 5, wherein obtaining the disparity comprises associating each feature point of a first one of the two images with a corresponding point of a second one of the two images; the method further comprising generating a stereoscopic cloud of the obstacle based on the feature points and the obstacle distance. ### Claim 7 (depends on 6) The method of claim 6, wherein directing the mobile platform comprises controlling the mobile platform based on at least one of the stereoscopic cloud, the obstacle distance, or the motion estimation. ### Claim 8 (depends on 7) The method of claim 7, wherein controlling the mobile platform comprises adjusting a movement status of the mobile platform. ### Claim 9 (depends on 8) The method of claim 8, wherein adjusting the movement status comprises changing or maintaining at least one of a velocity or a direction of the mobile platform. ### Claim 10 (depends on 1) The method of claim 1, wherein determining to use the detection mode comprises selecting a binocular mode as the detection mode and acquiring an obstacle distance using a binocular imaging device. ### Claim 11 (depends on 10) The method of claim 10, wherein acquiring the obstacle distance comprises: simultaneously capturing a first image with a first lens of the imaging device and capturing a second image with a second lens of the imaging device; determining a baseline between the first lens and the second lens; and calculating the obstacle distance using a binocular triangulation based on the first image, the second image, and the baseline. ### Claim 12 (depends on 10) The method of claim 10, wherein detecting the characteristic condition comprises performing motion estimation with the binocular mode. ### Claim 13 (depends on 12) The method of claim 12, wherein: performing the motion estimation with the binocular mode comprises determining a motion transformation between different times; and determining the motion transformation comprises acquiring a velocity, a rotation, and an orientation of the imaging device for the motion transformation. ### Claim 14 (depends on 13) The method of claim 13, wherein acquiring the velocity, the rotation, and the orientation comprises acquiring the velocity, the rotation, and the orientation via an inertial measurement unit (“IMU”). ### Claim 15 (depends on 1) The method of claim 1, wherein determining to use the detection mode comprises selecting a monocular mode as the detection mode and acquiring an obstacle distance with the monocular mode. ### Claim 16 (depends on 15) The method of claim 15, wherein acquiring the obstacle distance with the monocular mode comprises: capturing a first image and a second image of the obstacle using an imaging device at two different times with a predetermined monocular imaging interval; determining a displacement of the imaging device between the two different times; and calculating the obstacle distance via a monocular triangulation based on the first image, the second image, and the displacement. ### Claim 17 (depends on 16) The method of claim 16, wherein performing the motion estimation comprises performing the motion estimation with the monocular mode. ### Claim 18 (depends on 17) The method of claim 17, wherein: performing the motion estimation with the monocular mode comprises determining a plurality of transformations between two refreshing times; and determining the plurality of transformations comprises acquiring a velocity, a rotation, and an orientation of the imaging device for each of the plurality of transformations. ### Claim 19 An unmanned aerial vehicle (“UAV”), comprising: a plurality of propellers for providing a lifting power; and one or more processors, individually or collectively, operate to: determine a detection mode from a plurality of detection modes; detect a characteristic condition of the mobile platform with respect to an obstacle using the detection mode; and direct the UAV via the propellers to avoid the obstacle based on the detected characteristic condition. ### Claim 20 An apparatus for assisting obstacle avoidance of a mobile platform, comprising one or more processors, individually or collectively, operate to: determine to use a detection mode from a plurality of detection modes; detect a characteristic condition of the mobile platform with respect to an obstacle using the detection mode; and direct the mobile platform to avoid the obstacle based on the detected characteristic condition.